General

The final project is the main assignment of the course. Projects are required to be related in a reasonable way to at least one of the central topics of the course or related to human factors via the lens of computation. Final projects can be done in groups of 1–3 people; in our experience, groups of 3 lead to the best outcomes, so we encourage you to form a team of that size. Each project team will be assigned a mentor (a member of the teaching team), who will provide feedback on all their project-related work and generally be available.

Submission Format

The literature review, experiment protocol, and final paper must use the ICLR submission format and abide by all the ICLR requirements except where we have specified otherwise.

1. Project Proposal (👉 Oct 16, 11:59 PM PT)

This is a short paper (1–2 pages, excluding references) where you explain the problem you want to focus on for your final project, why it is important, and how it fits within the scope of CS329X. You should also briefly summarize why existing work and compare it to justify how your project builds upon it. Your goal is to clearly define a direction for your course project. This paper is not a full literature review; it's a focused justification of what you want to work on and why. You are encouraged to refer to relevant existing work, but only in service of motivating the problem.

The ideal is to keep the same topic for this proposal and the final project, but it’s fine if your direction changes over time. Your problem proposal will be graded on its own merits, regardless of what you do for the final project. Some guidance for structuring your paper:

  1. Problem Definition and Motivation: What is the core problem you want to address in your course project? Why is it meaningful, and to whom? Why is it a good fit for a human-centered LLM project?
  2. Comparison with Existing Work: Briefly describe what past work has tried to do in this area, and how it connects similarly or differently with your problem or why it falls short of fully addressing your problem. This can be due to limitations in model performance, lack of consideration for users, interaction issues, or other human-centered concerns.
  3. Next Steps and Direction: Suggest a possible approach or analysis plan for how you plan to tackle this problem in your course project.
  4. References Section: The entries should appear alphabetically and give at least full author name(s), year of publication, title, and outlet if applicable (e.g., journal name or proceedings name).

2. Midway Report (👉 Nov 6, 11:59 PM PT)

This is a short, structured report (5~6 pages, excluding references) designed to help you establish your core experimental/computational framework. No need to include “prior work discussion”. Grading will be mainly based on Data, Methods or Approaches and Summary of Progress.

Required sections:

  1. Research Questions: A statement of the project's core research questions (one paragraph)
  2. Data: A description of the dataset(s) that the project will use for either the analyses or evaluations.
  3. Methods or Approaches: A description of the methods or approaches that you'll be using, and a preliminary description of the approach that will be the focus of your investigation. At this early stage, some aspects of these approaches might not yet be worked out, so preliminary descriptions are fine.
  4. Summary of Progress: what you have been doing, what you still need to do, and any obstacles or concerns that might prevent your project from coming to fruition.
  5. References: In the same format as for literature review.

3. Final Project Report (👉 Dec 10, 11:59 PM PT)

The final paper should be 8 pages long, in ICLR submission format and adhering to ICLR guidelines concerning references, layout, supplementary materials, and so forth.

Below are the required components for the final paper:

  1. Introduction (2 points)
  2. Related Work (1 point)
  3. Data (1 points)
  4. Methods (5 points)
  5. Results (10 points)
  6. Discussion / Conclusion (1 point)

  7. Ethical Consideration: Please write an explicit discussion section of any potential ethical issues, such as around the ethical implication of the project, the use of the data, and potential applications of your work. Here are some recommendations from ACL's ethics guideline: "Ethical questions may arise when working with a variety of types of computational work with language, including (but not limited to) the collection and release of data, inference of information or judgments about individuals, real-world impact of the deployment of language technologies, and environmental consequences of large-scale computation."

  8. Authorship statement: At the end of your paper (after the 'Acknowledgments' section in the template), please include a brief authorship statement, explaining how the individual authors contributed to the project. You are free to include whatever information you deem important to convey. For guidance, see the second page, right column, of this guidance for PNAS authors (p. 12). We are requiring this largely because we think it is a good policy in general. This statement is required even for singly-authored papers, because we want to know whether your project is a collaboration with people outside of the class. Only in extreme cases, and after discussion with the team, would we consider giving separate grades to team members based on this statement.
  9. References